Presentation Language¶

By default, entities and tags of analysis or recommendation are reported in the language of the document or photo. However, we can request them in other languages as well (currently, Czech, Dutch, English, French, German, Polish, Portuguese, Slovak, and Spanish are supported) using the parameter presentationLanguage with the ISO code of the desired language.

Presentation Language in Article Content Analysis¶

Below, is an example reporting entities and tags in French. The code is the same as in this example with the exception of the presentationLanguage parameter.

const analyze = async (config, input) => {
    const response = await axios.post('nlp/analyze', input, config);
    return response.data;
};

const input = {
    id: '1234',
    title: 'Emmanuel Macron in Germany.',
    text: 'Mr. Macron visited a trade show in Munich.'
    presentationLanguage: 'fr'
}

analyze(config, input).then(report);

def analyze(input):
    return requests.post(f'{BASE_URL}nlp/analyze', json=input, headers=HEADERS).json()

input = {
    'id': '1234',
    'title': 'Emmanuel Macron in Germany.',
    'text': 'Mr. Macron visited a trade show in Munich.',
    'presentationLanguage': 'fr'
}

analyze(input)

from geneeanlpclient  import g3

requestBuilder = g3.Request.Builder(customConfig={'presentationLanguage': 'fr'})

with g3.Client.create(url=f'{BASE_URL}nlp/analyze") as analyzer:
    analyzer.session.headers.update({'X-API-Key': API_KEY})

    request = requestBuilder.build(id=str('1234'), title='Emmanuel Macron in Germany.', text='Mr. Macron visited a trade show in Munich.')
    result = analyzer.analyze(request)

    print("Entities:")
    for e in result.entities:
        print(f'   {e.type}: {e.stdForm} ({e.gkbId})')

    print("Tags:")
    for t in result.tags:
        print(f'   {t.type}: {t.stdForm} ({t.gkbId}) relevance: {t.relevance}')

produces the following result (see the Analysis reference page for explanation, Note that we have omitted the relations field for simplicity).

{
  version: '3.2.1',
  id: '1234',
  language: { detected: 'en' },
  entities: [
    { id: 'e0', gkbId: 'G57305', stdForm: 'salon', type: 'general' },
    { id: 'e1', gkbId: 'G183', stdForm: 'Allemagne', type: 'location' },
    { id: 'e2', gkbId: 'G1726', stdForm: 'Munich', type: 'location' },
    { id: 'e3', gkbId: 'G3052772', stdForm: 'Emmanuel Macron', type: 'person' },
    { id: 'e4', gkbId: 'G183', stdForm: 'Allemagne', type: 'country', feats: {derivedBy: 'gkb2:[gkbp:adminCountry]'} },
    { id: 'e5', gkbId: 'G980', stdForm: 'Bavière', type: 'region', feats: { derivedBy: 'gkb2:[gkbp:region]' } }
  ],
  tags: [
    { id: 't0', gkbId: 'G3052772', stdForm: 'Emmanuel Macron', type: 'media', relevance: 22.605, feats: { wikidataId: 'Q3052772' } },
    { id: 't1', gkbId: 'G183', stdForm: 'Allemagne', type: 'media', relevance: 18.365, feats: { wikidataId: 'Q183' } },
    { id: 't2', gkbId: 'G1726', stdForm: 'Munich', type: 'media', relevance: 7.57, feats: { wikidataId: 'Q1726' } }
  ],
  relations: [..],
  docSentiment: { mean: 0.0, label: 'neutral', positive: 0.0, negative: 0.0 },
  usedChars: 100
}

{
  'version': '3.2.1',
  'id': '1234',
  'language': { 'detected': 'en' },
  'entities': [
    { 'id': 'e0', 'gkbId': 'G57305', 'stdForm': 'salon', 'type': 'general' },
    { 'id': 'e1', 'gkbId': 'G183', 'stdForm': 'Allemagne', 'type': 'location' },
    { 'id': 'e2', 'gkbId': 'G1726', 'stdForm': 'Munich', 'type': 'location' },
    { 'id': 'e3', 'gkbId': 'G3052772', 'stdForm': 'Emmanuel Macron', 'type': 'person' },
    { 'id': 'e4', 'gkbId': 'G183', 'stdForm': 'Allemagne', 'type': 'country', 'feats': {'derivedBy': 'gkb2:[gkbp:adminCountry]'} },
    { 'id': 'e5', 'gkbId': 'G980', 'stdForm': 'Bavière', 'type': 'region', 'feats': { 'derivedBy': 'gkb2:[gkbp:region]' } }
  ],
  'tags': [
    { 'id': 't0', 'gkbId': 'G3052772', 'stdForm': 'Emmanuel Macron', 'type': 'media', 'relevance': 22.605, 'feats': { 'wikidataId': 'Q3052772' } },
    { 'id': 't1', 'gkbId': 'G183', 'stdForm': 'Allemagne', 'type': 'media', 'relevance': 18.365, 'feats': { 'wikidataId': 'Q183' } },
    { 'id': 't2', 'gkbId': 'G1726', 'stdForm': 'Munich', 'type': 'media', 'relevance': 7.57, 'feats': { 'wikidataId': 'Q1726' } }
  ],
  'relations': [..],
  'docSentiment': { 'mean': 0.0, 'label': 'neutral', 'positive': 0.0, 'negative': 0.0 },
  'usedChars': 100
}

Entities:
    general: salon (G57305)
    location: Allemagne (G183)
    location: Munich (G1726)
    person: Emmanuel Macron (G3052772)
    country: Allemagne (G183)
    region: Bavière (G980)
Tags:
    media: Emmanuel Macron (G3052772) relevance: 22.605
    media: Allemagne (G183) relevance: 18.365
    media: Munich (G1726) relevance: 7.57

Presentation Language in Photo Recommendation¶

Coming soon.

Multiple Presentation Languages¶

Sometimes more than one presentation language is needed. Obviously, we could perform repeated analyses or recommendations, each with one of the desired presentation language. However, it is typically faster to perform one analysis/recommendation and then ask the knowledgebase for translation of entities and tags to other languages.

For example, the following code, translates two tags (e.g., from a Photo Recommendations) to Polish:

const kbStdForms = async (input, config) => {
    const response = await axios.post('knowledgebase/stdforms', input, config)
    return response.data;
};

input = {
    ids: ['G458', 'G567'],
    language: 'pl',
};

kbStdForms(input, config).then(report);

def kbStdForms(input: Mapping[str, Any]):
    return requests.post(f'{BASE_URL}knowledgebase/stdforms', json=input, headers=HEADERS).json()

input = {
    'ids': ['G458', 'G567'],
    'language': 'pl',
};

kbStdForms(input)

kbStdForms(input, config).then(report);

{
  G458: { value: 'Unia Europejska', language: 'pl' },
  G567: { value: 'Angela Merkel', language: 'pl' }
}

{'G458': {'value': 'Unia Europejska', 'language': 'pl'},
 'G567': {'value': 'Angela Merkel', 'language': 'pl'}}